# Latest models, higher quality stems

AudioShake

January 22, 2024

Today [AudioShake](/content/site-root.html) is rolling out its new [instrument separation models](/content/instrument-stem-separation/index.html)–meaning, we have better stems for you!

The latest [improvements to our stems](https://www.youtube.com/watch?v=loDicxcTYTg) were made possible by better understanding the variety of playing styles and expressions of individual instruments. After expanding our engineering and research team and training a completely new architecture for months, our stems now offer:

- Reduced bleeding from other instruments into the source stems, meaning cleaner stems overall.
- More defined separation quality across vocal, bass, drum, and “other” stems.
- Snappier drums that retain more of the original transients, resulting in punchier kick drums and sharper cymbals.
- Deeper and cleaner bass notes, as well as improvements on expressive techniques such as slap bass.
- Well-balanced piano tones across a wide range of pianos.
- Vibrant guitar sounds with greatly improved sustain across a variety of effect pedals

AudioShake is deeply committed to building the [highest-quality sound separation models in the industry](/content/post/audioshake-sony-demixing-2023/index.html) so that they can be leveraged by creators, content owners, and developers. So we’ve made it a priority to make these models available to customers of all sizes, deploying them across [AudioShake Live](http://live.audioshake.ai/), [AudioShake Indie](http://indie.audioshake.ai/), and our [API](http://developer.audioshake.ai/).

## AudioShake introduces new models for all stems - YouTube

Tap to unmute

[AudioShake introduces new models for all stems](https://www.youtube.com/watch?v=PSxVT_ECClw) [AudioShake](https://www.youtube.com/channel/UC7olw-IdHcEQOJJPYAg1-Cw)

AudioShake610 subscribers

How do the new models stack up to others? Our vocal model is nearly 2dB better in SDR compared to the best open-source model (Demucs), and about 1dB better on average across all sources. (You can find [more information on SDR scores here](/content/post/audioshake-sony-demixing-2023/index.html)). As the industry leader in music stem separation, we’ve been incredibly fortunate to work with [artists, labels, publishers, producers, developers, and distributors](/content/case-studies/index.html) of all sizes, and have gotten to work on a number of great music projects this past year, including:

- [Remastering De La Soul’s first six albums for digital release](/content/post/de-la-soul/index.html)
- [Mastering _Fast X_’s soundtrack with Immersive Mixers](/content/case-study-fast-x/index.html)
- [A spatial mix of Nina Simone’s _Little Girl Blue_](/content/post/introducing-nina-simones-debut-album-to-new-audiences/index.html)
- [A full live album of Oscar Peterson](/content/post/a-live-broadcast-of-a-jazz-legend-is-brought-to-life-with-ai/index.html)
- [An ODB sample on SZA’s _SOS_](/content/case-study-rodney-jerkins/index.html)

We’ve also worked to make our technology available on other platforms–like [Chordal](https://www.chordal.com/) for sync licensing; [OOONA](https://ooona.net/), [Yella Umbrella](https://yellaumbrella.tv/), and [Cielo24](https://cielo24.com/) for localization–and to help power third-party applications like the mastering company [Masterchannel](https://masterchannel.ai/), AI mixing company [Tuney](https://www.tuney.io/), AR app [Minibeats](https://artiphon.com/), real-time stem separation on [djayPro](https://www.algoriddim.com/djay-pro-mac)—and many more.

For audio professionals, the quality difference will be clear. But we won’t stop here. We look forward to continued improvements in quality, speed, and access points in the years to come.